Interpretable machine learning models for the prediction of all‐cause mortality and time to death in hemodialysis patients
Therapeutic Apheresis and Dialysis · 2025
DOI: 10.1111/1744-9987.14212 ↗Kurz gefasst
Fachartikel in der Zeitschrift Therapeutic Apheresis and Dialysis, 2025. Verfasst von Minjie Chen und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Nephrology, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China. Hauptthemen laut MEDLINE: Renal Dialysis, Machine Learning, Kidney Failure, Chronic. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: the Guangzhou Municipal Science and Technology Project.
Abstract (Originalsprache)
Introduction
The elevated mortality and hospitalization rates among hemodialysis (HD) patients underscore the necessity for the development of accurate predictive tools. This study developed two models for predicting all‐cause mortality and time to death—one using a comprehensive database and another simpler model based on demographic and clinical data without laboratory tests.
Method
A retrospective cohort study was conducted from January 2017 to June 2023. Two models were created: Model A with 85 variables and Model B with 22 variables. We assessed the models using random forest (RF), support vector machine, and logistic regression, comparing their performance via the AU‐ROC. The RF regression model was used to predict time to death. To identify the most relevant factors for prediction, the Shapley value method was used.
Results
Among 359 HD patients, the RF model provided the most reliable prediction. The optimized Model A showed an AU‐ROC of 0.86 ± 0.07, a sensitivity of 0.86, and a specificity of 0.75 for predicting all‐cause mortality. It also had an R 2 of 0.59 for predicting time to death. The optimized Model B had an AU‐ROC of 0.80 ± 0.06, a sensitivity of 0.81, and a specificity of 0.70 for predicting all‐cause mortality. In addition, it had an R 2 of 0.81 for predicting time to death.
Conclusion
Two new interpretable clinical tools have been proposed to predict all‐cause mortality and time to death in HD patients using machine learning models. The minimal and readily accessible data on which Model B is based makes it a valuable tool for integrating into clinical decision‐making processes.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Nephrology, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China.
- School of Biomedical Engineering, Sun Yat-Sen University, Shenzhen, China.
- Depeartment of Electronic Engineering, Shantou University, Shantou, China.
ORCID-Profile: Yuanwen Xu
Förderung
- the Guangzhou Municipal Science and Technology Project
Zitieren
APA
Chen, M., Zeng, Y., Liu, M., Li, Z., Wu, J., Tian, X., Wang, Y., & Xu, Y. (2025). Interpretable machine learning models for the prediction of all‐cause mortality and time to death in hemodialysis patients. Therapeutic Apheresis and Dialysis. https://doi.org/10.1111/1744-9987.14212
Vancouver
Chen M, Zeng Y, Liu M, Li Z, Wu J, Tian X, et al. Interpretable machine learning models for the prediction of all‐cause mortality and time to death in hemodialysis patients. Therapeutic Apheresis and Dialysis. 2025. doi:10.1111/1744-9987.14212
BibTeX
@article{Chen2025,
author = {Chen, Minjie and Zeng, Youbing and Liu, Mengting and Li, Zhenghui and Wu, Jiazhen and Tian, Xuan and Wang, Yunuo and Xu, Yuanwen},
title = {Interpretable machine learning models for the prediction of all‐cause mortality and time to death in hemodialysis patients},
journal = {Therapeutic Apheresis and Dialysis},
year = {2025},
doi = {10.1111/1744-9987.14212}
}
EUVIMED